- Minitab Cookbook
- Isaac Newton
- 294字
- 2021-07-16 12:29:25
Checking if data follows a normal distribution
The normality test in basic statistics is a tool that is similar to the probability plot used in Chapter 2, Tables and Graphs. It is limited to testing normality but it does offer us the choice between Anderson-Darling statistics, Kolmogorov-Smirnov, and Ryan-Joiner tests.
Here, we will use the data from the Oxford weather station and check the normality of the mean maximum temperature for July.
Getting ready
The data for this example can be found on the Met Office website at http://www.metoffice.gov.uk/climate/uk/stationdata/oxforddata.txt.
The data is made available in the Oxford Weather.txtfile; this preserves the format from the website and also the Minitab Oxford weather (cleaned).mtwfile. This worksheet is correctly imported into Minitab for us. Follow steps 1 to 12 in the Producing a graphical summary of data recipe to import the results.
How to do it…
- Go to the Data menu and select Split Worksheet….
- In the By variables section, enter the column for month (C2 mm).
- Click on OK.
- From the new worksheets, select the worksheet for July.
- Go to the Stat menu and then Basic Statistics and click on Normality Test….
- In the dialog box, enter the column for mean maximum temperature in the Variable field.
- Click on OK.
How it works…
The output will give us means, standard deviation, the test statistic, and the P-value. The Anderson-Darling test is more sensitive to deviations from normality in the tails of the distribution.
- 新形勢下中國投入產出核算的變革與實踐
- 讓財報說話：世界500強CFO帶你輕松讀財報（鮮讀版）
- 博弈論及其在經濟管理中的應用
- Learning Informatica PowerCenter 9.x
- 企業能源審計與節能規劃
- Microsoft Dynamics CRM 2011 Scripting Cookbook
- 中國政府統計問題研究
- Microsoft Dynamics NAV
- 行政單位經濟責任審計實務指南
- Minitab Cookbook
- Business Intelligence Cookbook：A Project Lifecycle Approach Using Oracle Technology
- Big Data Analytics with R and Hadoop
- 統計原理與實務
- Managing Virtual Infrastructure with Veeam? ONE?
- Force.com Tips and Tricks